# Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach

arXiv: https://arxiv.org/abs/2309.04427 · HTML: https://mlsanity.com/paper/2309.04427/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 67 references that are in the map.
- First posted on arXiv 8 Sep 2023.

## Builds on (most cited first, 20 of 20)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [Privacy for Free: How does Dataset Condensation Help Privacy?](https://mlsanity.com/paper/2206.00240/) (2022)
- [DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation](https://mlsanity.com/paper/2002.11603/) (2020)
- [Variational Model Inversion Attacks](https://mlsanity.com/paper/2201.10787/) (2022)
- [Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network](https://mlsanity.com/paper/2106.07229/) (2021)
- [CryptoDL: Deep Neural Networks over Encrypted Data](https://mlsanity.com/paper/1711.05189/) (2017)
- [Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence](https://mlsanity.com/paper/2111.01177/) (2021)
- [Adversarial Learning of Privacy-Preserving and Task-Oriented Representations](https://mlsanity.com/paper/1911.10143/) (2019)
- [Precise Approximation of Convolutional Neural Networks for Homomorphically Encrypted Data](https://mlsanity.com/paper/2105.10879/) (2021)
- [Sparse Coding and Autoencoders](https://mlsanity.com/paper/1708.03735/) (2017)
- [Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation](https://mlsanity.com/paper/2205.01950/) (2022)
- [Label-only Model Inversion Attack: The Attack that Requires the Least Information](https://mlsanity.com/paper/2203.06555/) (2022)
- [DPGen: Automated Program Synthesis for Differential Privacy](https://mlsanity.com/paper/2109.07441/) (2021)
- [Less is More: Revisiting the Gaussian Mechanism for Differential Privacy](https://mlsanity.com/paper/2306.02256/) (2023)
- [Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings](https://mlsanity.com/paper/2211.05717/) (2022)
- [Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning](https://mlsanity.com/paper/2308.04960/) (2023)

## Built on by (most cited first, 2 of 2)

- [How Private Are DNA Embeddings? Inverting Foundation Model Representations of Genomic Sequences](https://mlsanity.com/paper/2603.06950/) (2026)
- [Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning](https://mlsanity.com/paper/2603.15842/) (2026)

## Abstract (arXiv)

Several domains increasingly rely on machine learning in their applications. The resulting heavy dependence on data has led to the emergence of various laws and regulations around data ethics and privacy and growing awareness of the need for privacy-preserving machine learning (ppML). Current ppML techniques utilize methods that are either purely based on cryptography, such as homomorphic encryption, or that introduce noise into the input, such as differential privacy. The main criticism given to those techniques is the fact that they either are too slow or they trade off a model s performance for improved confidentiality. To address this performance reduction, we aim to leverage robust representation learning as a way of encoding our data while optimizing the privacy-utility trade-off. Our method centers on training autoencoders in a multi-objective manner and then concatenating the latent and learned features from the encoding part as the encoded form of our data. Such a deep learning-powered encoding can then safely be sent to a third party for intensive training and hyperparameter tuning. With our proposed framework, we can share our data and use third party tools without being under the threat of revealing its original form. We empirically validate our results on unimodal and multimodal settings, the latter following a vertical splitting system and show improved performance over state-of-the-art.